Fabric Defect Detection Using Customized Deep Convolutional Neural Network for Circular Knitting Fabrics

Autor:	HATAMİ VARJOVİ, Mahdi, TALU, Muhammed Fatih, HANBAY, Kazım
Rok vydání:	2022
Předmět:	Engineering Complementary and alternative medicine Mühendislik Pharmaceutical Science Pharmacology (medical) Fabric defect classification Deep learning Neural networks Model optimization
Zdroj:	Volume: 11, Issue: 3 160-165 Turkish Journal of Nature and Science Türk Doğa ve Fen Dergisi
ISSN:	2149-6366
DOI:	10.46810/tdfd.1108264
Popis:	Visual inspection is a main stage of quality assurance process in many applications. In this paper, we propose a new network architecture for detecting the fabric defects based on convolutional neural network. Four different pre-trained and customized model network architectures have compared in terms of performance. Results has been evaluated on a fabric defect dataset of 13.800 images. Among the existing Inception V3, MobileNetV2, Xception and ResNet50 methods, the InceptionV3 model has achieved 78% classification success. Our designed deep network model could achieve 97% success. The experimental works show that the designed deep model is effective in detecting the fabric defects.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b9b86275ecfe8e85e78566fce73d213 https://doi.org/10.46810/tdfd.1108264 Zobrazit plný text záznamu